Orchestrates and routes academic manuscript development from topic selection through empirical identification and peer review for 《管理世界》…
Guides manuscript revisions and drafts point-by-point rebuttal letters tailored for Management World (《管理世界》) R&R submissions.
Activate ultra-compressed communication mode that drops ~75% token usage by eliminating articles, filler, pleasantries, and hedging while…
Report estimated context window utilization and flag when approaching the compaction threshold
Audit and curate the 5-layer agent context hierarchy to prevent quality degradation mid-session — rules files, specs, source files, error…
Relentlessly interview the user about a plan or design, walking down every branch of the decision tree one question at a time until…
Enforce vertical-slice discipline — implement one thin slice (~100 lines max), test it, verify it works, commit it, then repeat.
Extract requirements one targeted question at a time before any plan or code starts — hypothesizes user intent, scores confidence, and…
Record, list, search, and apply cross-session learnings — capture insights from completed work as JSONL entries so patterns persist across…
Run a YC-style office hours session before writing code — six forcing questions that surface wrong premises, missing constraints, and…
Internal health check skill for AI DevStudio project.
Run a weekly retrospective — what shipped, what broke, what slowed you down, and what to change next week.
Convert a bug fix, repeated workaround, or solved problem into a permanent, testable Claude Code skill.
Gated 4-phase workflow (Specify → Plan → Tasks → Implement) where nothing advances without explicit human review — surfaces assumptions…
Synthesize the current conversation context and codebase into a full PRD — problem statement, user stories, implementation decisions…
A skill that cannot be invoked by the model.
Convert requirements into buildable, testable work.
Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.
Name and bootstrap a new MarbleLabs project.
Format final answer as markdown and copy to clipboard.
Fires when a fellow proposes bringing an external/market skill into the studio repo — "found a skill for X on skills.sh", "should we add…